{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T5JGLSQFQJ4GH55DYJVSRG43YP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9c5d1bb224099ee8cbee3260d329ced94a3935dbe24be4fa1c6d093615eb7868","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T19:12:09Z","title_canon_sha256":"a06b08f9ff4c05e2fcc0ced30af1e67649d3d11449792dfc21119205985e99b0"},"schema_version":"1.0","source":{"id":"2606.07643","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07643","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07643v1","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07643","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"T5JGLSQFQJ4G","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"T5JGLSQFQJ4GH55D","created_at":"2026-06-09T00:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"T5JGLSQF","created_at":"2026-06-09T00:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:ea8dbd352f2ad4ebcb273977c060df4254ba26c80d4142236bbdb540a425b6a7","target":"graph","created_at":"2026-06-09T00:04:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.07643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their audio-visual intelligence (AVI) remains insufficiently evaluated due to the lack of systematic and comprehensive benchmarks. We introduce AVI-Bench, a cognitively inspired benchmark that evaluates Omni-MLLMs across three stages, perception, understanding, and reasoning, through cross-modal tasks requiring joint audio-visual interpretation. This design enables fine-grained diagnosis of model capabilities and failure modes. To further assess robustn","authors_text":"Cheng Liang, Guangyao Li, Hao Fei, Henghui Ding, Shaoxuan Xu, Weijun Wang, Wenjie Du, Wenming Tu, Yaoting Wang, Yuanchao Li, Yuanchun Li, Yunxin Liu, Ziyi Zhang","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T19:12:09Z","title":"AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07643","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6ee4ed471783ac0b011e62c5c496ee8159fb3a36c00f5e2a5f6713d10ec11018","target":"record","created_at":"2026-06-09T00:04:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9c5d1bb224099ee8cbee3260d329ced94a3935dbe24be4fa1c6d093615eb7868","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T19:12:09Z","title_canon_sha256":"a06b08f9ff4c05e2fcc0ced30af1e67649d3d11449792dfc21119205985e99b0"},"schema_version":"1.0","source":{"id":"2606.07643","kind":"arxiv","version":1}},"canonical_sha256":"9f5265ca05827863f7a3c26b289b9bc3eb8ccd5b2e7a482fe1e6161da5fd991c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f5265ca05827863f7a3c26b289b9bc3eb8ccd5b2e7a482fe1e6161da5fd991c","first_computed_at":"2026-06-09T00:04:45.663255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:45.663255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ynp+Gfqp89l1jXsLSWqxA/pAF2NlaWp3L7/DIFCa5qZHm8u82HDH0Wzd6CcrUM4LU0Np81ZUBFgAR/Y7AAtLBg==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:45.663623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07643","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ee4ed471783ac0b011e62c5c496ee8159fb3a36c00f5e2a5f6713d10ec11018","sha256:ea8dbd352f2ad4ebcb273977c060df4254ba26c80d4142236bbdb540a425b6a7"],"state_sha256":"ce5d2ac41596f7bd64bf8a51f837410cc25c047026144d0b548ce064799ecaa8"}